Method and apparatus for voice modification during a call

Abstract

A method for voice modification during a telephone call comprising receiving a source audio signal associated with at least one participant, wherein the source audio signal comprises a voice of the at least one participant, detecting a source dialect of the at least one participant, selecting a target dialect based on at least a characteristic of a target participant and creating a modulated audio signal based on the source audio signal, the source dialect, and the target dialect and transmitting the modulated audio signal to the target participant.

The invention claimed is: 
     
       1. A method for voice modification during a telephone call comprising:
 receiving a source audio signal associated with at least one participant, wherein the source audio signal comprises a voice of the at least one participant; 
 detecting a source dialect of the at least one participant; 
 selecting a target dialect based on at least a characteristic of a target participant; 
 creating a modulated audio signal based on the source audio signal, the source dialect, and the target dialect; 
 transmitting the modulated audio signal to the target participant 
 analyzing the modulated voice of the participant to determine whether the modulation was successful; 
 adjusting the modulation when the modulation is not successful; and 
 determining whether the modulation was successful based on feedback from the at least one participant. 
 
     
     
       2. The method of  claim 1  wherein creating a modulated audio signal comprises:
 converting an audio signal associated with the participant voice to a source text; 
 selecting a speech profile based on metadata associated with the target participant; 
 transforming the source text into modified text based on the speech profile; and 
 converting the modified text to speech, based on the selected speech profile. 
 
     
     
       3. The method of  claim 2 , wherein the speech profile comprises at least one of region information, dialect information, phonetic transformation information or acoustic information. 
     
     
       4. The method of  claim 2 , wherein the metadata comprises at least one of a caller ID of the target participant, a user ID of the target participant, or information derived from a social media account of the target participant. 
     
     
       5. The method of  claim 2 , wherein creating a modulated audio signal occurs in response to detecting that a target accent threshold has been exceeded. 
     
     
       6. The method of  claim 1 , further comprising:
 transmitting the source audio signal to at least one participant other than the target participant. 
 
     
     
       7. An apparatus for voice modification during a telephone call comprising:
 a detection module that receives a source audio signal associated with at least one participant, wherein the source audio signal comprises a voice of the at least one participant, selects a source dialect of the participant voice based on at least one of a location of the participant, a geographic area where the participant has checked-in most frequently, a birthplace of the participant, or a location where the participant studied, and selects a target dialect based on at least a characteristic of a target participant; and 
 a modulation module that creates a modulated audio signal based on the source audio signal, the source dialect, and the target dialect, transmits the modulated audio signal to the target participant, analyzes the modulated voice of the participant to determine whether the modulation was successful, adjusts the modulation when the modulation is not successful, and determines whether the modulation was successful based on feedback from the at least one participant. 
 
     
     
       8. The apparatus of  claim 7 , further comprising:
 a conversion module that converts an audio signal associated with the participant voice to a source text, selects a speech profile based on metadata associated with the target participant, transforms the source text into modified text based on the speech profile and converts the modified text to speech, based on the selected speech profile. 
 
     
     
       9. The apparatus of  claim 8 , wherein the speech profile comprises at least one of region information, dialect information, phonetic transformation information or acoustic information. 
     
     
       10. The apparatus of  claim 8 , wherein the metadata comprises at least one of a caller ID of the target participant, a user ID of the target participant, or information derived from a social media account of the target participant. 
     
     
       11. The apparatus of  claim 8 , wherein creating a modulated audio signal occurs in response to detecting that a target accent threshold has been exceeded. 
     
     
       12. The apparatus of  claim 7 , wherein the apparatus further transmits the source audio signal to at least one participant other than the target participant.